© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 125574
    Prev
    Next
    INDEX
    Explanations

    noun followed by continuation

    np_acts-logits-general · gemini-2.5-flash-lite

    Salt, Value, panic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﻬ
    0.57
    strate
    0.53
     consejos
    0.51
     excepciones
    0.50
    ate
    0.50
    லுக்கு
    0.49
     игре
    0.48
     இல
    0.48
     dedicado
    0.47
    icus
    0.47
    POSITIVE LOGITS
    K
    0.49
     uuid
    0.47
     можуть
    0.46
    陞
    0.45
    F
    0.44
    ไม่
    0.44
    Ré
    0.43
     Reykjavik
    0.42
    Waar
    0.41
    Kana
    0.41
    Activations Density 0.000%

    No Known Activations